Date: Tue, 16 Sep 2014 15:50:03 +0200 From: Carsten Mattner <carstenmattner@gmail.com> To: Konstantin Belousov <kostikbel@gmail.com> Cc: freebsd-arch@freebsd.org Subject: Re: Intel MPX (Skylake ISA) support? Message-ID: <CACY%2BHvrFg-86cuDzd_ePRcx1UZhGfxSTV_8jNJuoQcB0SzZXXw@mail.gmail.com> In-Reply-To: <20140916083343.GS2737@kib.kiev.ua> References: <CACY%2BHvoMDFLJLy7hz3guJNrJH8gmi5Vh9-rYeRErr2JgDhV2yw@mail.gmail.com> <20140913162059.GU2737@kib.kiev.ua> <CACY%2BHvqKYhXzPgvK8CWpp4NMcD2_c3xzownVBk6O=8_4PiM%2Bjw@mail.gmail.com> <20140914090033.GA2737@kib.kiev.ua> <CACY%2BHvqGGhfqVaNuvxDdkmAzK6wX1wVv4V5Pw3uZZhfJNH_2zw@mail.gmail.com> <20140916083343.GS2737@kib.kiev.ua>
next in thread | previous in thread | raw e-mail | index | archive | help
On Tue, Sep 16, 2014 at 10:33 AM, Konstantin Belousov <kostikbel@gmail.com> wrote: > On Sun, Sep 14, 2014 at 11:18:09AM +0200, Carsten Mattner wrote: >> More details I was able to find with links to hopefully descriptive >> documentation. IIUC developers have been using a well known >> Intel CPU simulator, but I'm in the dark there. > SDE does not run on FreeBSD, and setting up Linux (or Windows) for this > is out of question, at least for me. > >> >> gcc: http://gcc.gnu.org/wiki/Intel%20MPX%20support%20in%20the%20GCC%20compiler >> >> glibc: >> https://sourceware.org/ml/libc-alpha/2014-03/msg00491.html >> https://sourceware.org/ml/libc-alpha/2014-03/msg00543.html >> https://sourceware.org/ml/libc-alpha/2014-03/msg00605.html > > I can google as well. I have no intend of reverse-engineering Linux code > to get basic information about CPU core. > > Why are you so insisted on the non-released feature, which seemingly > still lacks complete documentation ? Yes, something can be done even > now, but that requires a lot of efforts, backed by a huge belief into > the world-shaking nature of the MPX and inability to wait even a bit to After going over the chapter in the ISA pdf the feature doesn't look as useful as I thought it would be and it's only to prevent buffer underrun/overrun - no other widespread vector is closed. > get hands on it. I do not have that urge, and do not understand why do > you try to trick others into it. Will you provide the hardware to the > developers when it become generally avaiable ? Sorry you think I'm trying to trick anyone - that couldn't be further from the truth but English is not my native language and I maybe misrepresented the question. > FWIW, it would be very useful if Jim Harris chimed in.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?CACY%2BHvrFg-86cuDzd_ePRcx1UZhGfxSTV_8jNJuoQcB0SzZXXw>